匹配行，创建列组并按组在R中求和列组

我有一个巨大的数据集，大约30000行，17000列，还有一个字符元素向量

这是一个虚拟集，它重新创建了我的数据集

### Example

df <- data.frame(Gene=paste0("gene", 1:60), replicate(60, runif(60, min=0, max=100)))
colnames(df) <- c("GeneName", paste0("TisA.", 1:20), paste0("TisB.", 1:20), paste0("TisC.", 1:20))

genes <- sample(df$GeneName, 5)

head(df)
#      GeneName    TisA.1    TisA.2    TisA.3   TisA.4
#1    gene1  1.987621 17.936562 18.145417 59.43023
#2    gene2 60.031713 73.822846 93.946769 72.27633
#3    gene3 44.833748 47.890719 77.100497 39.45719
#4    gene4 44.662776 26.285659 30.087606 49.50682
#5    gene5 63.770411  6.469006  3.797708 68.17532

然而，我被困在这里了，哪种方法最快可以为基因分配等级，并将这些等级按组相加，即TisA、TisB和TisC

为了澄清，每组有20个样品TisA.1、TisA.2、…、TisA.20

期望的输出是：

 GeneName   TisA TisB TisC
    gene4     24   32   10 ## these are random values to show sum of ranks for each of genes in the vector
    gene1     14   12   20 ## these are random values to show sum of ranks for each of genes in the vector
   gene40      4   92   12 ## these are random values to show sum of ranks for each of genes in the vector
    gene2     64    2   40 ## these are random values to show sum of ranks for each of genes in the vector
   gene15     84   32    9 ## these are random values to show sum of ranks for each of genes in the vector

---

p.S我的真实数据集中的一些值可以是0，并且可以使用tidyverse在不同的列中重复

# your data. Including seed to make it reproducible
set.seed(123)
df <- data.frame(Gene=paste0("gene", 1:60), replicate(60, runif(60, min=0, max=100)))
colnames(df) <- c("GeneName", paste0("TisA.", 1:20), paste0("TisB.", 1:20), paste0("TisC.", 1:20))

library(tidyverse)
as.tbl(df) %>% 
    gather(key, value, -GeneName) %>% 
    group_by(GeneName) %>% 
    mutate(Ranks = rank(value, ties.method = "first"))  %>% 
    separate(key, into = c("key1", "key2"), sep = "[.]") %>% 
    group_by(GeneName,key1) %>% 
    summarise(Sum=sum(Ranks)) %>% 
    spread(key1, Sum)
# A tibble: 60 x 4
# Groups:   GeneName [60]
GeneName  TisA  TisB  TisC
*   <fctr> <int> <int> <int>
1    gene1   698   620   512
2   gene10   525   653   652
3   gene11   631   598   601
4   gene12   487   679   664
5   gene13   688   579   563
6   gene14   674   581   575
7   gene15   618   647   565
8   gene16   696   552   582
9   gene17   656   560   614
10  gene18   543   649   638 

或者尝试一个更基本的解决方案……有点复杂

df1 <- apply(df[-1], 1, rank, ties.method= "first")
df2 <- apply(df1, 2, function(x){
  aggregate(x, list(sapply(strsplit(colnames(df), "[.]"), "[", 1)[-1]), sum)
  })
df3 <- cbind.data.frame(df$GeneName, t(Reduce(cbind, lapply(df2, "[", 2))))
colnames(df3) <- c("GeneName",  "TisA", "TisB", "TisC")
head(df3[order(df3$GeneName),])
GeneName TisA TisB TisC
   gene1  698  620  512
  gene10  525  653  652
  gene11  631  598  601
  gene12  487  679  664
  gene13  688  579  563
  gene14  674  581  575

---

你在说什么类型的团体？您的基因标记为1-60，您有60行。该组将为TisA、TisB或TisC，每个组有20个元素，例如TisA.1、TisA.2、…TisA.20感谢Jimbou，如果colnames组信息（即TisA.1、TisA.2）存储在data.frame中，并且我的数据集中的实际列将是字母和数字的组合，这将是一种更简单的方法？

# your data. Including seed to make it reproducible
set.seed(123)
df <- data.frame(Gene=paste0("gene", 1:60), replicate(60, runif(60, min=0, max=100)))
colnames(df) <- c("GeneName", paste0("TisA.", 1:20), paste0("TisB.", 1:20), paste0("TisC.", 1:20))

library(tidyverse)
as.tbl(df) %>% 
    gather(key, value, -GeneName) %>% 
    group_by(GeneName) %>% 
    mutate(Ranks = rank(value, ties.method = "first"))  %>% 
    separate(key, into = c("key1", "key2"), sep = "[.]") %>% 
    group_by(GeneName,key1) %>% 
    summarise(Sum=sum(Ranks)) %>% 
    spread(key1, Sum)
# A tibble: 60 x 4
# Groups:   GeneName [60]
GeneName  TisA  TisB  TisC
*   <fctr> <int> <int> <int>
1    gene1   698   620   512
2   gene10   525   653   652
3   gene11   631   598   601
4   gene12   487   679   664
5   gene13   688   579   563
6   gene14   674   581   575
7   gene15   618   647   565
8   gene16   696   552   582
9   gene17   656   560   614
10  gene18   543   649   638 

df1 <- apply(df[-1], 1, rank, ties.method= "first")
df2 <- apply(df1, 2, function(x){
  aggregate(x, list(sapply(strsplit(colnames(df), "[.]"), "[", 1)[-1]), sum)
  })
df3 <- cbind.data.frame(df$GeneName, t(Reduce(cbind, lapply(df2, "[", 2))))
colnames(df3) <- c("GeneName",  "TisA", "TisB", "TisC")
head(df3[order(df3$GeneName),])
GeneName TisA TisB TisC
   gene1  698  620  512
  gene10  525  653  652
  gene11  631  598  601
  gene12  487  679  664
  gene13  688  579  563
  gene14  674  581  575